© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62489
    Prev
    Next
    INDEX
    Explanations

    effectiveness and efficacy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ç»ħ
    -0.09
    elize
    -0.09
    çIJ¬
    -0.09
    没äºĭ
    -0.09
     hä
    -0.09
     Forg
    -0.09
    edom
    -0.09
    ients
    -0.09
    å°ıå§ijå¨ĺ
    -0.09
    æı®
    -0.08
    POSITIVE LOGITS
    iveness
    0.10
    fully
    0.09
    æľĢ大åĮĸ
    0.09
    æѤ类
    0.09
    åij½
    0.09
    ä½ĵçİ°åľ¨
    0.08
    /right
    0.08
    æºIJæ³ī
    0.08
    ä¸Ģ次
    0.08
    å¾Ģä¸ĭ
    0.08
    Activations Density 0.121%

    No Known Activations